BP neural network optimization based on an improved genetic algorithm

An improved genetic algorithm based on evolutionarily stable strategy is proposed to optimize the initial weights of backpropagation (BP) network in this paper. The improvement of GA lies in the introducing of a new mutation operator under control of a stable factor, which is found to be a very simple and effective searching operator. The experimental results in BP neural network optimization show that this algorithm can effectively avoid BP network converging to local optimum. It is found by comparison that the improved, genetic algorithm can almost avoid the trap of local optimum and effectively improve the convergent speed.